{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IJIVH4V7H24XBUAFFPVVYTRLNO","short_pith_number":"pith:IJIVH4V7","schema_version":"1.0","canonical_sha256":"425153f2bf3eb970d0052beb5c4e2b6b8e2301f95d09252c50820ffb397b6d19","source":{"kind":"arxiv","id":"2305.16404","version":1},"attestation_state":"computed","paper":{"title":"GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bing Wang, Bo Li, Bo Yang, Zihui Zhang","submitted_at":"2023-05-25T18:11:21Z","abstract_excerpt":"We study the problem of 3D semantic segmentation from raw point clouds. Unlike existing methods which primarily rely on a large amount of human annotations for training neural networks, we propose the first purely unsupervised method, called GrowSP, to successfully identify complex semantic classes for every point in 3D scenes, without needing any type of human labels or pretrained models. The key to our approach is to discover 3D semantic elements via progressive growing of superpoints. Our method consists of three major components, 1) the feature extractor to learn per-point features from in"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.16404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-25T18:11:21Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"43baa26a9d0ebbf0bf43e7034ee270fa4890f3283f0eccd7a8199368e734cf20","abstract_canon_sha256":"a78ce3abf28bc337f7698d1344ce6e72f4c4ba6d3ba253db2f86042ba9c773a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:12.734199Z","signature_b64":"cA8mrpIpG8WJ2/yodhh59HnhuIJy3wYqCzDgismw16+Ts/JKMxBFY0VNaDY4ieF4BV+KY8yPwvyApXm/jEUgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"425153f2bf3eb970d0052beb5c4e2b6b8e2301f95d09252c50820ffb397b6d19","last_reissued_at":"2026-07-05T06:14:12.733831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:12.733831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bing Wang, Bo Li, Bo Yang, Zihui Zhang","submitted_at":"2023-05-25T18:11:21Z","abstract_excerpt":"We study the problem of 3D semantic segmentation from raw point clouds. Unlike existing methods which primarily rely on a large amount of human annotations for training neural networks, we propose the first purely unsupervised method, called GrowSP, to successfully identify complex semantic classes for every point in 3D scenes, without needing any type of human labels or pretrained models. The key to our approach is to discover 3D semantic elements via progressive growing of superpoints. Our method consists of three major components, 1) the feature extractor to learn per-point features from in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16404","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.16404/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.16404","created_at":"2026-07-05T06:14:12.733884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16404v1","created_at":"2026-07-05T06:14:12.733884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16404","created_at":"2026-07-05T06:14:12.733884+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJIVH4V7H24X","created_at":"2026-07-05T06:14:12.733884+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJIVH4V7H24XBUAF","created_at":"2026-07-05T06:14:12.733884+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJIVH4V7","created_at":"2026-07-05T06:14:12.733884+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03901","citing_title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJIVH4V7H24XBUAFFPVVYTRLNO","json":"https://pith.science/pith/IJIVH4V7H24XBUAFFPVVYTRLNO.json","graph_json":"https://pith.science/api/pith-number/IJIVH4V7H24XBUAFFPVVYTRLNO/graph.json","events_json":"https://pith.science/api/pith-number/IJIVH4V7H24XBUAFFPVVYTRLNO/events.json","paper":"https://pith.science/paper/IJIVH4V7"},"agent_actions":{"view_html":"https://pith.science/pith/IJIVH4V7H24XBUAFFPVVYTRLNO","download_json":"https://pith.science/pith/IJIVH4V7H24XBUAFFPVVYTRLNO.json","view_paper":"https://pith.science/paper/IJIVH4V7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16404&json=true","fetch_graph":"https://pith.science/api/pith-number/IJIVH4V7H24XBUAFFPVVYTRLNO/graph.json","fetch_events":"https://pith.science/api/pith-number/IJIVH4V7H24XBUAFFPVVYTRLNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJIVH4V7H24XBUAFFPVVYTRLNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJIVH4V7H24XBUAFFPVVYTRLNO/action/storage_attestation","attest_author":"https://pith.science/pith/IJIVH4V7H24XBUAFFPVVYTRLNO/action/author_attestation","sign_citation":"https://pith.science/pith/IJIVH4V7H24XBUAFFPVVYTRLNO/action/citation_signature","submit_replication":"https://pith.science/pith/IJIVH4V7H24XBUAFFPVVYTRLNO/action/replication_record"}},"created_at":"2026-07-05T06:14:12.733884+00:00","updated_at":"2026-07-05T06:14:12.733884+00:00"}